---
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: zephyr-7b-dpo-lora
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# zephyr-7b-dpo-lora

This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5263
- Rewards/chosen: -0.1493
- Rewards/rejected: -0.8998
- Rewards/accuracies: 0.7480
- Rewards/margins: 0.7505
- Logps/rejected: -228.2820
- Logps/chosen: -266.1538
- Logits/rejected: -1.9412
- Logits/chosen: -2.0663

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.5506        | 1.0   | 968  | 0.5556          | -0.1128        | -0.6425          | 0.7120             | 0.5297          | -225.7089      | -265.7884    | -1.9914         | -2.1123       |
| 0.545         | 2.0   | 1937 | 0.5313          | -0.1468        | -0.8623          | 0.7440             | 0.7156          | -227.9077      | -266.1287    | -1.9506         | -2.0746       |
| 0.5342        | 3.0   | 2904 | 0.5263          | -0.1493        | -0.8998          | 0.7480             | 0.7505          | -228.2820      | -266.1538    | -1.9412         | -2.0663       |


### Framework versions

- Transformers 4.35.0
- Pytorch 2.1.1+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1